HHFHNet: Hybrid Deep Learning Network for Course Recommendation Using H‐Matrix

Transactions on Emerging Telecommunications Technologies, Год журнала: 2025, Номер 36(4)

Опубликована: Март 20, 2025

ABSTRACT Background Students often need help choosing the right courses to complete their degrees. Course recommender systems assist in selecting suitable academic courses. Recent attention‐based have been developed distinguish influence of past on recommendations. However, these models might not work well when users diverse interests, because effectiveness attention mechanism decreases with variety historical To overcome issues, this study introduces a new approach called Hierarchical Attention Network Deep Learning for Text Forward Harmonic Net (HHFHNet) course recommendations using H‐matrix. Methods Initially, input data obtained from dataset is processed into overview and genres. After that, Term Frequency‐Inverse Document Frequency (TF‐IDF) method applied both query, resulting output fed HHFHNet, which combines Texts (HDLTex) Networks (HAN). This generates Recommendation Probability Value (CRPV), used retrieve recommended Simultaneously, specific genre features are selected chord distance. Then, These CRPV then H‐matrix create ranking‐based Finally, Explainable Artificial Intelligence (XAI) utilized generate recommendation messages based ranking approach. Results The HHFHNet technique was evaluated performance metrics such as precision, recall, F‐measure, it achieved values 90.31%, 91.87%, 91.08%, respectively. Conclusions proposed significantly enhances accuracy offers robust solution guiding students selection.

Язык: Английский

A hierarchical attention neural network with multi-view fusion for online course recommendation

Knowledge and Information Systems, Год журнала: 2025, Номер unknown

Опубликована: Май 2, 2025

Язык: Английский

Meta concept recommendation based on knowledge graph

Deleted Journal, Год журнала: 2024, Номер 27(1)

Опубликована: Сен. 16, 2024

Язык: Английский